INDEX

Explanations

terms related to scoring and performance metrics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orp

-0.16

ault

-0.16

ekil

-0.15

lad

-0.15

IMS

-0.15

iser

-0.14

ector

-0.14

 Lear

-0.14

las

-0.14

MLElement

-0.14

POSITIVE LOGITS

card

0.20

cards

0.18

occo

0.18

rupa

0.17

agenta

0.17

à¸¸à¸ĩ

0.17

keeping

0.16

regor

0.16

boards

0.15

ossa

0.15

Activations Density 0.022%

terms related to scoring and performance metrics

No Comments

No Known Activations